Processamento dos dados
data_files_selected <-
list.files(
pattern = ".*rafael.*resultado.*csv$",
recursive = TRUE,
ignore.case = TRUE
)
data_files_and_size <-
sapply(data_files_selected, file.size)
files_to_include_in_dataframe <-
tibble(
"Files" = names(data_files_and_size),
"Size (in MB)" = data_files_and_size/1E6
)
skimr::skim(files_to_include_in_dataframe)
Data summary
| Name |
files_to_include_in_dataf… |
| Number of rows |
2 |
| Number of columns |
2 |
| _______________________ |
|
| Column type frequency: |
|
| character |
1 |
| numeric |
1 |
| ________________________ |
|
| Group variables |
None |
Variable type: character
Variable type: numeric
| Size (in MB) |
0 |
1 |
0.87 |
0.49 |
0.52 |
0.69 |
0.87 |
1.04 |
1.21 |
▇▁▁▁▇ |
cdr <- load_cdr(names(data_files_and_size))
cdr %<>%
mutate(
expgroup = case_when(
str_detect(file, "rafael") ~ "rafael",
TRUE ~ "unknown"),
cycle = case_when(
str_detect(file, "R0") ~ "R0",
str_detect(file, "R4") ~ "R4",
TRUE ~ "unknown"),
time = case_when(
str_detect(file, "Initial") ~ "initial",
str_detect(file, "Final") ~ "final",
TRUE ~ "unknown")) %>%
select(cdr3, cycle, time, expgroup, everything())
cdr %<>%
group_by(cdr3, expgroup) %>%
arrange(cycle, desc(time), .by_group = TRUE) %>%
mutate(
fcp = cdrp / lag(cdrp, default = first(cdrp)),
fcq = quantity / lag(quantity, default = first(quantity))
) %>%
select(cdr3:quantity, fcp, fcq, everything())
cdr %>%
filter(time == "final") %>%
group_by(expgroup, cycle, time) %>%
arrange(desc(fcp)) %>%
slice_head(prop = .1) %>%
# slice_head(n = 1000) %>%
ggplot(aes(expgroup, log10(fcp))) +
geom_violin(aes(fill = expgroup, color = expgroup), alpha = 0.5) +
geom_jitter(aes(shape = expgroup), alpha = 0.6, size = 1) +
stat_summary(
fun = mean,
fun.min = mean,
fun.max = mean,
geom = "crossbar",
# width = 0.5,
aes(color = expgroup)
) +
facet_grid(. ~ cycle)

# cdr %>%
# filter(str_detect(cycle, "R0")) %>%
# filter(time == "final") %>%
# group_by(expgroup, cycle, time) %>%
# arrange(desc(fcp)) %>%
# slice_head(n = 1000) %>%
# ggplot(aes(fcp, color = expgroup, fill = expgroup)) +
# geom_density(stat = "bin", alpha = 0.3) +
# facet_grid(cycle ~ expgroup)
cdr %<>%
group_by(expgroup, cycle, time) %>%
arrange(desc(fcp)) %>%
slice_head(prop = .1) %>%
mutate(
threshold = mean(log10(fcp))
) %>%
mutate(
rich = if_else(
(log10(fcp) >= threshold) &
# (time == "final") &
# (str_detect(cycle, "R0")),
(time == "final"),
"rich",
"medium")) %>%
full_join(cdr) %>%
mutate(
rich = if_else(
is.na(rich),
"poor",
rich)) %>%
mutate(
rich = factor(rich,
levels = c("rich", "medium", "poor"))
) %>%
mutate(
threshold = if_else(
is.na(threshold),
0,
threshold
)
)
cdr %>%
filter(rich == "rich") %>%
ggplot() +
geom_violin(aes(expgroup, log10(fcp), fill = expgroup)) +
geom_jitter(aes(expgroup, log10(fcp), shape = expgroup), alpha = .2) +
facet_grid(rich ~ cycle)

cdr %>%
filter(!rich == "rich") %>%
ggplot() +
geom_violin(aes(expgroup, log10(fcp), fill = expgroup)) +
geom_jitter(aes(expgroup, log10(fcp), shape = expgroup), alpha = .2) +
facet_grid(rich ~ cycle)

## [1] "cdr3" "cycle" "time" "expgroup" "cdrp" "quantity"
## [7] "fcp" "fcq" "length" "MW" "AV" "IP"
## [13] "flex" "gravy" "SSF_Helix" "SSF_Turn" "SSF_Sheet" "n_A"
## [19] "n_C" "n_D" "n_E" "n_F" "n_G" "n_H"
## [25] "n_I" "n_K" "n_L" "n_M" "n_N" "n_P"
## [31] "n_Q" "n_R" "n_S" "n_T" "n_V" "n_W"
## [37] "n_Y" "aliphatic" "aromatic" "neutral" "positive" "negative"
## [43] "invalid" "file" "threshold" "rich"
cdr %>%
ggplot() +
geom_density(aes(AV, color = rich)) +
facet_grid(cycle ~ .)

cdr %>%
ggplot() +
geom_density(aes(MW, color = rich)) +
facet_grid(cycle ~ .)

cdr %>%
ggplot() +
geom_density(aes(gravy, color = rich)) +
facet_grid(cycle ~ .)

cdr %>%
ggplot() +
geom_density(aes(SSF_Turn, color = rich)) +
facet_grid(cycle ~ .)

cdr %>%
ggplot() +
geom_density(aes(IP, color = rich)) +
facet_grid(cycle ~ .)

cdr %>%
ggplot() +
geom_density(aes(flex, color = rich)) +
facet_grid(cycle ~ .)

cdr %>%
ggplot(aes(cycle, MW)) +
geom_violin(aes(fill = rich)) +
geom_jitter(alpha = .1) +
facet_grid(rich ~ cycle)

cdr %>%
filter(rich == "rich") %>%
ungroup() %>%
select(cdr3:SSF_Sheet & !c("cycle", "time", "expgroup")) -> rich66
rich66
## # A tibble: 109 x 14
## cdr3 cdrp quantity fcp fcq length MW AV IP flex gravy
## <chr> <dbl> <int> <dbl> <dbl> <int> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 GGVN… 0.0112 620 252. 310 8 889. 0.125 4.05 0.780 -1.44
## 2 APAG… 0.00456 252 205. 252 9 1025. 0.222 4.37 0.760 -0.933
## 3 PLTG… 0.00420 232 189. 232 7 800. 0.143 7.17 0.717 0.0571
## 4 VQES… 0.00371 205 167. 205 10 1133. 0.1 4.05 0.760 -0.09
## 5 DPGH… 0.00351 194 158. 194 8 875. 0.125 4.05 0.807 -2.17
## 6 DREV… 0.00337 186 151. 186 15 1834. 0.133 4.72 0.762 -1.24
## 7 DIRW… 0.00322 178 145. 178 14 1747. 0.214 4.54 0.751 -0.993
## 8 ETWG… 0.00610 337 137. 168. 7 881. 0.286 4.05 0.774 -1.7
## 9 EDGY… 0.00280 155 126. 155 10 1173. 0.4 4.05 0.735 -1.42
## 10 DLHW… 0.00277 153 124. 153 9 1065. 0.111 5.05 0.752 -0.833
## # … with 99 more rows, and 3 more variables: SSF_Helix <dbl>, SSF_Turn <dbl>,
## # SSF_Sheet <dbl>
## [1] "cdr3" "cycle" "time" "expgroup" "cdrp" "quantity"
## [7] "fcp" "fcq" "length" "MW" "AV" "IP"
## [13] "flex" "gravy" "SSF_Helix" "SSF_Turn" "SSF_Sheet" "n_A"
## [19] "n_C" "n_D" "n_E" "n_F" "n_G" "n_H"
## [25] "n_I" "n_K" "n_L" "n_M" "n_N" "n_P"
## [31] "n_Q" "n_R" "n_S" "n_T" "n_V" "n_W"
## [37] "n_Y" "aliphatic" "aromatic" "neutral" "positive" "negative"
## [43] "invalid" "file" "threshold" "rich"
cdr %>%
filter(cycle == "R4") %>%
ggplot() +
geom_violin(aes(rich, gravy, color = rich)) +
geom_jitter(aes(rich, gravy), alpha = .1)

Tentativa de Clusterização
Clusterization with Quantity and Prevalence variables
library(Rtsne)
set.seed(42)
tsne_df <- cdr %>%
filter(time == "final") %>%
filter(cycle == "R4")
tsne_df %>%
summarise(across(everything(), ~ all(sum(is.na(.x))))) %>%
select(where(isTRUE))
## # A tibble: 1 x 2
## # Groups: expgroup, cycle [1]
## expgroup cycle
## <chr> <chr>
## 1 rafael R4
tsne_df %>%
filter(is.na(threshold)) %>%
select(rich, threshold, quantity)
## # A tibble: 0 x 6
## # Groups: expgroup, cycle, time [0]
## # … with 6 variables: expgroup <chr>, cycle <chr>, time <chr>, rich <fct>,
## # threshold <dbl>, quantity <int>
set.seed(42)
tsne_out <-
tsne_df %>%
ungroup() %>%
select(!where(is.character)) %>%
select(!c(which(apply(., 2, var)==0))) %>%
unique() %>%
Rtsne(
X = .,
dims = 3,
perplexity = 30,
theta = 0.5,
max_iter = 1E3,
verbose = T,
pca_center = T,
pca_scale = T,
# partial_pca = T,
normalize = T,
eta = 200.0,
exaggeration_factor = 12.0,
num_threads = parallel::detectCores()
)
## Performing PCA
## Read the 5684 x 42 data matrix successfully!
## OpenMP is working. 8 threads.
## Using no_dims = 3, perplexity = 30.000000, and theta = 0.500000
## Computing input similarities...
## Building tree...
## Done in 7.41 seconds (sparsity = 0.023010)!
## Learning embedding...
## Iteration 50: error is 90.878403 (50 iterations in 20.01 seconds)
## Iteration 100: error is 87.416493 (50 iterations in 14.37 seconds)
## Iteration 150: error is 86.914374 (50 iterations in 12.42 seconds)
## Iteration 200: error is 86.814880 (50 iterations in 11.74 seconds)
## Iteration 250: error is 86.763858 (50 iterations in 11.32 seconds)
## Iteration 300: error is 2.619334 (50 iterations in 12.31 seconds)
## Iteration 350: error is 2.144671 (50 iterations in 10.42 seconds)
## Iteration 400: error is 1.925249 (50 iterations in 10.57 seconds)
## Iteration 450: error is 1.796627 (50 iterations in 11.97 seconds)
## Iteration 500: error is 1.713050 (50 iterations in 10.91 seconds)
## Iteration 550: error is 1.658394 (50 iterations in 11.48 seconds)
## Iteration 600: error is 1.622142 (50 iterations in 12.35 seconds)
## Iteration 650: error is 1.595243 (50 iterations in 10.85 seconds)
## Iteration 700: error is 1.577939 (50 iterations in 11.29 seconds)
## Iteration 750: error is 1.566228 (50 iterations in 11.54 seconds)
## Iteration 800: error is 1.557336 (50 iterations in 11.24 seconds)
## Iteration 850: error is 1.549330 (50 iterations in 11.46 seconds)
## Iteration 900: error is 1.542255 (50 iterations in 11.90 seconds)
## Iteration 950: error is 1.536608 (50 iterations in 11.45 seconds)
## Iteration 1000: error is 1.531498 (50 iterations in 11.39 seconds)
## Fitting performed in 240.98 seconds.
tsne_df %>%
ungroup() %>%
select(!where(is.character)) %>%
select(!c(which(apply(., 2, var)==0))) %>%
unique() -> a
tsne_out %>%
.$Y %>%
as_tibble() %>%
ggplot() +
geom_point(aes(V1, V2, color = a$rich))

tsne_out %>%
.$Y %>%
as_tibble() %>%
plot_ly(
title = "Sample title",
x = .$V1,
y = .$V2,
z = .$V3,
type = "scatter3d",
mode = "markers",
color = a$rich
) %>%
layout(title = "With Quantity Variables")
Clusterization only with Biochemistry Properties
library(Rtsne)
set.seed(42)
tsne_df <- cdr %>%
filter(time == "final") %>%
filter(cycle == "R4")
tsne_df %>%
summarise(across(everything(), ~ all(sum(is.na(.x))))) %>%
select(where(isTRUE))
## # A tibble: 1 x 2
## # Groups: expgroup, cycle [1]
## expgroup cycle
## <chr> <chr>
## 1 rafael R4
tsne_df %>%
filter(is.na(threshold)) %>%
select(rich, threshold, quantity)
## # A tibble: 0 x 6
## # Groups: expgroup, cycle, time [0]
## # … with 6 variables: expgroup <chr>, cycle <chr>, time <chr>, rich <fct>,
## # threshold <dbl>, quantity <int>
set.seed(42)
tsne_out <-
tsne_df %>%
ungroup() %>%
select(cdr3, !where(is.character)) %>%
select(!c(which(apply(., 2, var)==0))) %>%
select(!c("quantity", "cdrp", "fcp", "fcq", "rich", "threshold")) %>%
mutate(cdr3 = as.factor(cdr3)) %>%
Rtsne(
X = .,
dims = 3,
perplexity = 30,
theta = 0.5,
max_iter = 1E3,
verbose = T,
pca_center = T,
pca_scale = T,
normalize = T,
partial_pca = T,
eta = 200.0,
exaggeration_factor = 12.0,
num_threads = parallel::detectCores()
)
## Performing PCA
## Read the 5753 x 50 data matrix successfully!
## OpenMP is working. 8 threads.
## Using no_dims = 3, perplexity = 30.000000, and theta = 0.500000
## Computing input similarities...
## Building tree...
## Done in 8.83 seconds (sparsity = 0.024285)!
## Learning embedding...
## Iteration 50: error is 89.876509 (50 iterations in 13.17 seconds)
## Iteration 100: error is 89.838613 (50 iterations in 18.20 seconds)
## Iteration 150: error is 89.539497 (50 iterations in 14.79 seconds)
## Iteration 200: error is 89.513348 (50 iterations in 13.55 seconds)
## Iteration 250: error is 89.493390 (50 iterations in 13.23 seconds)
## Iteration 300: error is 3.177528 (50 iterations in 11.87 seconds)
## Iteration 350: error is 2.706362 (50 iterations in 11.36 seconds)
## Iteration 400: error is 2.501842 (50 iterations in 10.47 seconds)
## Iteration 450: error is 2.384828 (50 iterations in 11.75 seconds)
## Iteration 500: error is 2.309165 (50 iterations in 11.86 seconds)
## Iteration 550: error is 2.256507 (50 iterations in 10.81 seconds)
## Iteration 600: error is 2.219267 (50 iterations in 10.78 seconds)
## Iteration 650: error is 2.192489 (50 iterations in 11.42 seconds)
## Iteration 700: error is 2.175055 (50 iterations in 10.53 seconds)
## Iteration 750: error is 2.163736 (50 iterations in 10.42 seconds)
## Iteration 800: error is 2.155068 (50 iterations in 11.13 seconds)
## Iteration 850: error is 2.148645 (50 iterations in 10.90 seconds)
## Iteration 900: error is 2.143209 (50 iterations in 10.75 seconds)
## Iteration 950: error is 2.138527 (50 iterations in 10.71 seconds)
## Iteration 1000: error is 2.134156 (50 iterations in 11.91 seconds)
## Fitting performed in 239.61 seconds.
tsne_df %>%
ungroup() %>%
select(cdr3, !where(is.character)) %>%
select(!c(which(apply(., 2, var)==0))) %>%
select(!c("quantity", "cdrp", "fcp", "fcq", "threshold")) -> a
tsne_out %>%
.$Y %>%
as_tibble() %>%
ggplot() +
geom_point(aes(V1, V2, color = a$rich))

tsne_out %>%
.$Y %>%
as_tibble() %>%
plot_ly(
x = .$V1,
y = .$V2,
z = .$V3,
type = "scatter3d",
mode = "markers",
color = a$rich
) %>%
layout(title = "Without Quantity Variables")